ClawHub
Back to skill

Security audit

MoltMon

Security checks across malware telemetry and agentic risk

Overview

MoltMon is a disclosed digital-pet game with user-run Python scripts, local game-state behavior, and optional multiplayer features, with no artifact-backed malicious behavior found.

Install only if you are comfortable running the bundled Python game scripts. Treat pet names, owner IDs, and any online messages as public/non-sensitive, and enable online or A2A features only deliberately.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill advertises and appears to rely on capabilities including network access, file read/write, and possibly environment access, but does not declare any permissions. That creates a transparency and least-privilege failure: hosts or users cannot accurately assess what the skill may access, and the A2A multiplayer/web portal context increases exposure because external communication is a core feature rather than incidental.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal